Blind Source Separation Method Research Articles

Insights Into Brain Network Dynamics Across Ages Using Group-ICA Functional Parcellation

Aging is a natural and inevitable process in human life that involves changes in the brain. The brain becomes structurally, functionally, and interconnected differently. The evolution of brain activity and its anatomy follows separate paths, causing them to not always align. Independent Component Analysis (ICA), a Blind Source Separation (BSS) method, enables brain parcellation considering an individual's functional patterns. This is advantageous when studying brain function at different stages of life, allowing for a more comprehensive and flexible approach that accounts for age-related differences. This study aims to investigate the relationship between age and functional networks, exploring the differences in the functional parcellations of two different age groups and their networks. We propose a method utilizing group-ICA that identifies functional connectivity patterns to estimate coherent networks. We found variations in the distribution of the age-related networks and the brain portions they covered; some networks in old adults encompassed smaller areas in comparison to the networks in young adults.

Main lobe deceptive jamming suppression based on blind source separation and energy detection for monopulse radar

AbstractMain lobe deceptive jamming always causes the serious degradation of signal detection ability and angle measurement precision of monopulse radar. In recent years, the Blind Source Separation (BSS) method has been adopted to suppress the main lobe jamming. However, the separation results of BSS have the problem of amplitude ambiguity, which will cause the radar using monopulse angle measurement fail to measure the angle parameters after jamming suppression. To tackle this problem, a novel main lobe jamming suppression method is proposed based on BSS and energy detection. Firstly, the models of target echoes and jamming in the sum and difference beam receiving channels are derived. Secondly, the target echoes and interferences are separated by the Joint Approximate Diagonalisation of Eigenmatrices (JADE) algorithm, and then the unperturbed signal segments in the mixed signal are extracted by energy detection, thereby obtaining the precise ratio of the sum and difference channels to complete the angle measurement. Performance of the method was verified by numerical simulation. The results show that the proposed method can achieve interference suppression while accurately estimating the angle parameter of the target.

Modelling multivariate spatio-temporal data with identifiable variational autoencoders

Modelling multivariate spatio-temporal data with complex dependency structures is a challenging task but can be simplified by assuming that the original variables are generated from independent latent components. If these components are found, they can be modelled univariately. Blind source separation aims to recover the latent components by estimating the unknown linear or nonlinear unmixing transformation based on the observed data only. In this paper, we extend recently introduced identifiable variational autoencoder to the nonlinear nonstationary spatio-temporal blind source separation setting and demonstrate its performance using comprehensive simulation studies. Additionally, we introduce two alternative methods for the latent dimension estimation, which is a crucial task in order to obtain the correct latent representation. Finally, we illustrate the proposed methods using a meteorological application, where we estimate the latent dimension and the latent components, interpret the components, and show how nonstationarity can be accounted and prediction accuracy can be improved by using the proposed nonlinear blind source separation method as a preprocessing method.

A Non-Invasive Fetal QRS Complex Detection Method Based on a Multi-Feature Fusion Neural Network

Fetal heart monitoring, as a crucial part of fetal monitoring, can accurately reflect the fetus’s health status in a timely manner. To address the issues of high computational cost, inability to observe fetal heart morphology, and insufficient accuracy associated with the traditional method of calculating the fetal heart rate using a four-channel maternal electrocardiogram (ECG), a method for extracting fetal QRS complexes from a single-channel non-invasive fetal ECG based on a multi-feature fusion neural network is proposed. Firstly, a signal entropy data quality detection algorithm based on the blind source separation method is designed to select maternal ECG signals that meet the quality requirements from all channel ECG data, followed by data preprocessing operations such as denoising and normalization on the signals. After being segmented by the sliding window method, the maternal ECG signals are calculated as data in four modes: time domain, frequency domain, time–frequency domain, and data eigenvalues. Finally, the deep neural network using three multi-feature fusion strategies—feature-level fusion, decision-level fusion, and model-level fusion—achieves the effect of quickly identifying fetal QRS complexes. Among the proposed networks, the one with the best performance has an accuracy of 95.85% and sensitivity of 97%.

Diagnosing multiple faults in rotating machinery using empirical mode decomposition and blind source separation methods

It is a challenging task to accurately diagnose multiple faults in a rotating machinery. In this paper, the authors have used empirical mode decomposition (EMD) and blind source separation (BSS) methods for this purpose. A portable rotating machinery setup is made in the laboratory and faults such as bearing inner and outer race faults, angular misalignment are created into it. The vibration data is collected using SPM made LEONOVA DIAMOND(r) FFT analyzer and processed using CONDMASTER RUBY(r) and MATLAB(r) softwares. Firstly, wavelet transform is applied to the signal to denoise it. After this, EMD is implemented to decompose the signal into different intrinsic mode functions (IMFs). After preprocessing these IMFs using the principal component analysis (PCA), BSS is used to extract fault-related information from the IMFs. A comparison of the results obtained from EMD and PCA-BSS is also presented in the paper. Keywords: Rotating machinery, Multiple faults, Vibration data, Wavelet transform, Empirical mode decomposition, Blind source separation, Principal component analysis.

Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform

Compared to parametric counterparts, non-parametric (aka, model-free) damage detection methods have no requirements of accurate models, with the potential of autonomous monitoring of various complex structures. However, noises, or low signal-to-noise ratio (SNR), are one of the main challenges. This study is aimed at improving blind source separation (BSS)-based damage detection method, one of the most advanced non-parametric methods, in both aspects of noise robustness and autonomous operation. In particular, the measured acceleration responses are processed by variational mode decomposition (VMD) and wavelet transform (WT) in sequential, acting as the input for a BSS model. The BSS is then solved by independent component analysis (ICA), which approves to be more noise-robust compared to the state-of-the-art counterparts. Furthermore, shapelet transform is applied to extract the universal shape-based spike-like feature from the BSS model for training a support vector machine (SVM) model, applicable to different structures; it finally automates the sudden damage detection process and enables online monitoring. The effectiveness of the proposed method is illustrated by a numerical example and an experimental test, and demonstrated by a real-world seismic-excited structure. The results show that both single and multiple sudden damages can be automatically detected with high accuracy. Compared with the existing BSS methods, the proposed BSS method is more capable to detect small damages at relatively low SNR. In addition, the classification accuracy of SVM is also improved when shapelet-based feature is used for training, which reduces the malfunction of automated damage detection as shown by the numerical example. Therefore, the proposed strategy has the potential for rapid condition assessment of structures during rare/extreme events, before engineers are sent for further post-event inspection.

Three layered sparse dictionary learning algorithm for enhancing the subject wise segregation of brain networks

Independent component analysis (ICA) and dictionary learning (DL) are the most successful blind source separation (BSS) methods for functional magnetic resonance imaging (fMRI) data analysis. However, ICA to higher and DL to lower extent may suffer from performance degradation by the presence of anomalous observations in the recovered time courses (TCs) and high overlaps among spatial maps (SMs). This paper addressed both problems using a novel three-layered sparse DL (TLSDL) algorithm that incorporated prior information in the dictionary update process and recovered full-rank outlier-free TCs from highly corrupted measurements. The associated sequential DL model involved factorizing each subject’s data into a multi-subject (MS) dictionary and MS sparse code while imposing a low-rank and a sparse matrix decomposition restriction on the dictionary matrix. It is derived by solving three layers of feature extraction and component estimation. The first and second layers captured brain regions with low and moderate spatial overlaps, respectively. The third layer that segregated regions with significant spatial overlaps solved a sequence of vector decomposition problems using the proximal alternating linearized minimization (PALM) method and solved a decomposition restriction using the alternating directions method (ALM). It learned outlier-free dynamics that integrate spatiotemporal diversities across brains and external information. It differs from existing DL methods owing to its unique optimization model, which incorporates prior knowledge, subject-wise/multi-subject representation matrices, and outlier handling. The TLSDL algorithm was compared with existing dictionary learning algorithms using experimental and synthetic fMRI datasets to verify its performance. Overall, the mean correlation value was found to be 26%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$26\\%$$\\end{document} higher for the TLSDL than for the state-of-the-art subject-wise sequential DL (swsDL) technique.

A dynamic generative model can extract interpretable oscillatory components from multichannel neurophysiological recordings.

Modern neurophysiological recordings are performed using multichannel sensor arrays that are able to record activity in an increasingly high number of channels numbering in the 100s to 1000s. Often, underlying lower-dimensional patterns of activity are responsible for the observed dynamics, but these representations are difficult to reliably identify using existing methods that attempt to summarize multivariate relationships in a post hoc manner from univariate analyses or using current blind source separation methods. While such methods can reveal appealing patterns of activity, determining the number of components to include, assessing their statistical significance, and interpreting them requires extensive manual intervention and subjective judgment in practice. These difficulties with component selection and interpretation occur in large part because these methods lack a generative model for the underlying spatio-temporal dynamics. Here, we describe a novel component analysis method anchored by a generative model where each source is described by a bio-physically inspired state-space representation. The parameters governing this representation readily capture the oscillatory temporal dynamics of the components, so we refer to it as oscillation component analysis. These parameters - the oscillatory properties, the component mixing weights at the sensors, and the number of oscillations - all are inferred in a data-driven fashion within a Bayesian framework employing an instance of the expectation maximization algorithm. We analyze high-dimensional electroencephalography and magnetoencephalography recordings from human studies to illustrate the potential utility of this method for neuroscience data.

Underdetermined Blind Source Separation of Audio Signals for Group Reared Pigs Based on Sparse Component Analysis.

In order to solve the problem of difficult separation of audio signals collected in pig environments, this study proposes an underdetermined blind source separation (UBSS) method based on sparsification theory. The audio signals obtained by mixing the audio signals of pigs in different states with different coefficients are taken as observation signals, and the mixing matrix is first estimated from the observation signals using the improved AP clustering method based on the "two-step method" of sparse component analysis (SCA), and then the audio signals of pigs are reconstructed by L1-paradigm separation. Five different types of pig audio are selected for experiments to explore the effects of duration and mixing matrix on the blind source separation algorithm by controlling the audio duration and mixing matrix, respectively. With three source signals and two observed signals, the reconstructed signal metrics corresponding to different durations and different mixing matrices perform well. The similarity coefficient is above 0.8, the average recovered signal-to-noise ratio is above 8 dB, and the normalized mean square error is below 0.02. The experimental results show that different audio durations and different mixing matrices have certain effects on the UBSS algorithm, so the recording duration and the spatial location of the recording device need to be considered in practical applications. Compared with the classical UBSS algorithm, the proposed algorithm outperforms the classical blind source separation algorithm in estimating the mixing matrix and separating the mixed audio, which improves the reconstruction quality.

Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters

Objective. Developing neural decoders robust to non-stationary conditions is essential to ensure their long-term accuracy and stability. This is particularly important when decoding the neural drive to muscles during dynamic contractions, which pose significant challenges for stationary decoders. Approach. We propose a novel adaptive electromyography (EMG) decomposition algorithm that builds on blind source separation methods by leveraging the Kullback–Leibler divergence and kurtosis of the signals as metrics for online learning. The proposed approach provides a theoretical framework to tune the adaptation hyperparameters and compensate for non-stationarities in the mixing matrix, such as due to dynamic contractions, and to identify the underlying motor neuron (MN) discharges. The adaptation is performed in real-time (∼22 ms of computational time per 100 ms batches). Main results. The hyperparameters of the proposed adaptation captured anatomical differences between recording locations (forearm vs wrist) and generalised across subjects. Once optimised, the proposed adaptation algorithm significantly improved all decomposition performance metrics with respect to the absence of adaptation in a wide range of motion of the wrist (80∘). The rate of agreement, sensitivity, and precision were ⩾90% in ⩾80% of the cases in both simulated and experimentally recorded data, according to a two-source validation approach. Significance. The findings demonstrate the suitability of the proposed online learning metrics and hyperparameter optimisation to compensate the induced modulation and accurately decode MN discharges in dynamic conditions. Moreover, the study proposes an experimental validation method for EMG decomposition in dynamic tasks.

Comparing the three-dimensional morphological asymmetries in the ejecta of Kepler and Tycho in X-rays

Aims. Recent simulations have shown that asymmetries in the ejecta distribution of supernova remnants (SNRs) may be a reflection of asymmetries left over from the initial supernova explosion. Thus, SNR studies provide a vital means for testing and constraining model predictions in relation to the distribution of heavy elements, which are key to improving our understanding of the explosion mechanisms in Type Ia supernovae. Methods. The use of a novel blind source separation method applied to the megasecond X-ray observations of the historic Kepler and Tycho supernova remnants has revealed maps of the ejecta distribution. These maps are endowed with an unprecedented level of detail and clear separations from the continuum emission. Our method also provides a three-dimensional (3D) view of the ejecta by individually disentangling red- and blueshifted spectral components associated with images of the Si, S, Ar, Ca, and Fe emission. This approach provides insights into the morphology of the ejecta distribution in those two remnants. Results. Those mappings have allowed us to thoroughly investigate the asymmetries in the intermediate-mass elements and Fe distribution in two Type Ia supernova remnants. We also compared the results with the core-collapse Cassiopeia A remnant, which we had studied previously. The images obtained confirm, as expected for Type Ia SNRs, that the Fe distribution is mostly closer to the core than that of intermediate-mass elements. They also highlight peculiar features in the ejecta distribution, such as the Fe-rich southeastern knot in Tycho.

Unveiling Hidden Sources of Dynamic Functional Connectome through a Novel Regularized Blind Source Separation Approach

Abstract The investigation of the brain’s functional connectome and its dynamic changes can provide valuable insights into brain organization and its reconfiguration. However, the analysis of dynamic functional connectivity (dFC) using functional magnetic resonance imaging (fMRI) faces major challenges, including the high dimensionality of brain networks, unknown latent sources underlying observed dFC, and the large number of brain connections that increase the risk of spurious findings. In this paper, we propose a new regularized blind source separation (BSS) method called dyna-LOCUS to address these challenges. dyna-LOCUS decomposes observed dFC measures to reveal latent source connectivity traits and their dynamic temporal expression profiles. By utilizing low-rank factorization and novel regularizations, dyna-LOCUS achieves efficient and reliable mapping of connectivity traits underlying the dynamic brain functional connectome, characterizes temporal changes of the connectivity traits that contribute to the reconfiguration in the observed dFC, and generates parsimonious and interpretable results in identifying whole-brain dFC states. We introduce a highly efficient iterative Node-Rotation algorithm that solves the non-convex optimization problem for learning dyna-LOCUS. Simulation studies demonstrate the advantages of our proposed method. Application of dyna-LOCUS to the Philadelphia Neurodevelopmental Cohort (PNC) study unveils latent connectivity traits and key brain connections and regions driving each of these neural circuits, reveals temporal expressions and interactions of these connectivity traits, and generates new findings regarding gender differences in the neurodevelopment of an executive function-related connectivity trait.

Joint dereverberation and blind source separation using a hybrid autoregressive and convolutive transfer function-based model

Most frequency-domain blind source separation (BSS) methods are based on the multiplicative narrowband assumption, which is not valid in long reverberation environments. In contrast, convolutive transfer function (CTF)-based BSS methods do not rely on the narrowband assumption, and the separation performance is significantly improved compared to the traditional algorithms in long reverberation environments. However, the CTF-based BSS methods and their variants, e.g., autoregressive (AR) BSS methods, introduce modeling errors to some extent, due to the truncation or approximation during the optimization process. To address this problem, we propose a frequency-domain BSS method employing a hybrid AR and CTF model, which can provide more precise representations of the early reflections and late reverberations. Furthermore, we utilize the Gaussian noise model to deal with the BSS problem in noisy reverberant environments. We formulate the objective function using the maximum log-likelihood criterion, and derive an efficient iterative algorithm for parameter estimation with the block coordinate descent (BCD) method. Experimental results show that the proposed method has a better separation performance than the existing methods in long reverberation environments.

Non-contact air-coupled transducers Lamb wave signal multipath effect and blind separation for different modes using PZT as receiver

Due to the complexity and faintness of the detection wave patterns obtained by air-coupled transducers, if it is possible to effectively separate the various modes and obtain non-dispersive signals for more accurate detection and positioning, it will help to improve the accuracy and reliability of air-coupled ultrasonic Lamb wave detection, providing better technical support for the application and development of related fields. Because of the increased complexity of air-coupled signals, there is no definite theoretical formula to describe the mode changes of air-coupled signals, so the method based on blind separation has unique value. To address these challenges, the paper proposes a single-channel blind source separation (SCBSS) method. The effectiveness of this method is evaluated through simulations and experiments, demonstrating favorable separation results and efficient computational speed. This work first conducts an in-depth analysis of the signal characteristics of air-coupled ultrasonic non-destructive testing, and simulates the ultrasonic excitation conditions of air-coupled sensors through finite element software. The study of modal changes and multipath effects caused by the variation of the incidence angle of the ACT signal is carried out, and the situation of the Lamb wave signal excited by ACT at the receiving end is analyzed. By combining ACT with PZT signals, the ultrasonic signals of air-coupled Lamb waves are compared and studied, and their modal purification is carried out.

Methods for Processing Physiological Artifacts in Single/Few-Channel EEG Signals

Electroencephalogram (EEG) is a non-invasive measurement method of brain electrical activity. In recent years, single/few-channel EEG has been used more and more, but various types of physiological artifacts seriously affect the analysis and wide application of single/few-channel EEG. In this paper, the regression and filtering methods, decomposition methods, blind source separation methods and machine learning methods involved in the various physiological artifacts in single/few-channel EEG are reviewed. According to the characteristics of single/few-channel EEG signals, hybrid EEG artifact removal methods for different scenarios are analyzed and summarized, mainly including single-artifact/multi-artifact scenes and online/offline scenes. In addition, the methods and metrics for validating the performance of the algorithm on semi-simulated and real EEG data are also reviewed. Finally, the development trend of single/few-channel EEG application and physiological artifact processing is briefly described.

Ship-Radiated Noise Separation in Underwater Acoustic Environments Using a Deep Time-Domain Network

Ship-radiated noise separation is critical in both military and economic domains. However, due to the complex underwater environments with multiple noise sources and reverberation, separating ship-radiated noise poses a significant challenge. Traditionally, underwater acoustic signal separation has employed blind source separation methods based on independent component analysis. Recently, the separation of underwater acoustic signals has been approached as a deep learning problem. This involves learning the features of ship-radiated noise from training data. This paper introduces a deep time-domain network for ship-radiated noise separation by leveraging the power of parallel dilated convolution and group convolution. The separation layer employs parallel dilated convolution operations with varying expansion factors to better extract low-frequency features from the signal envelope while preserving detailed information. Additionally, we use group convolution to reduce the expansion of network size caused by parallel convolution operations, enabling the network to maintain a smaller size and computational complexity while achieving good separation performance. The proposed approach is demonstrated to be superior to the other common networks in the DeepShip dataset through comprehensive comparisons.

Improvements of EEG Signal Quality: A Hybrid Method of Blind Source Separation and Variational Mode Destruction to Reduce Artifacts

The electroencephalogram (EEG) is a crucial tool for studying brain activity; yet it frequently encounters artifacts that distort meaningful neural signals. This paper addresses the challenge of artifact removal through a unique hybrid method, combining Variational Mode Decomposition (VMD) techniques with Blind Source Separation (BSS) algorithms. VMD, recognized for its adaptability to non-linear and non-stationary EEG data, as well as its ability to alleviate mode mixing and the “endpoint effect,” which serves as an effective preprocessing step. The paper evaluates the performance of two integrated BSS algorithms, AMICA and AMUSE, across various criteria. Comparisons across metrics such as Euclidean distance, Spearman correlation coefficient, and Root Mean Square Error reveal similar performance between AMICA and AMUSE. However, a distinct divergence is evident in the Signal to Artifact Ratio (SAR). When employed with VMD, AMICA demonstrates superiority in effectively discerning and segregating brain signals from artifacts, which gives a mean value of 1.0924. This study introduces a potent hybrid VMDBSS approach for enhancing EEG signal quality. The findings emphasize the notable impact of AMICA, particularly in achieving optimal results in artifact removal, as indicated by its superior performance in SAR. The abstract concludes by underlining the significance of these results, emphasizing AMICA’s pivotal role in achieving the highest measurable evaluation value, making it a compelling choice for researchers and practitioners in EEG signal processing.

Research on heart and lung sound separation method based on DAE–NMF–VMD

Auscultation is the most effective method for diagnosing cardiovascular and respiratory diseases. However, stethoscopes typically capture mixed signals of heart and lung sounds, which can affect the auscultation effect of doctors. Therefore, the efficient separation of mixed heart and lung sound signals plays a crucial role in improving the diagnosis of cardiovascular and respiratory diseases. In this paper, we propose a blind source separation method for heart and lung sounds based on deep autoencoder (DAE), nonnegative matrix factorization (NMF) and variational mode decomposition (VMD). Firstly, DAE is employed to extract highly informative features from the heart and lung sound signals. Subsequently, NMF clustering is applied to group the heart and lung sounds based on their distinct periodicities, achieving the separation of the mixed heart and lung sounds. Finally, variational mode decomposition is used for denoising the separated signals. Experimental results demonstrate that the proposed method effectively separates heart and lung sound signals and exhibits significant advantages in terms of standardized evaluation metrics when compared to contrast methods.

Utilizing data-driven algorithms for blind modal parameter identification of structures from output-only video measurements

In structural dynamics and vibration analysis, modal identification plays a pivotal role in understanding and characterizing the dynamic behavior of complex systems. Traditional modal analysis techniques heavily rely on accurate sensor placement and knowledge of the excitation forces, which may not always be feasible or practical in real-world scenarios. Recently, non-contact video-based modal analysis methods for structures with arbitrary complexity using computer vision techniques have gained much importance. But these methods need to know ahead of time where the structure's natural frequency ranges are, and they use steerable pyramids, which are complicated multi-scale image decomposition filters. To address these issues, a blind modal identification technique is suggested to extract the modal parameters (modal frequency and mode shapes) from the recorded structural vibration video signal. The proposed algorithm for unsupervised machine learning is the Non-Negative Matrix Factorization (NNMF) method, which is combined with the Generalized Complexity Pursuit (GCP) method for blind source separation. The NNMF algorithm is directly applied to the raw pixel-time series made from the video data to get the temporal components, which are then separated using GCP to find the individual modal frequencies and mode shapes. The above algorithm is first validated on a numerical model and then implemented on laboratory scale models (cantilever, single-degree, and multi-degree frame models). Finally, the proposed methodology is implemented on real-world recorded structural vibration videos to determine its noise sensitivity, such as the Tacoma Narrows bridge and the London Millennium footbridge. The modal parameters extracted are compared with those from the available literature for validation. The estimation errors obtained from all the validations are well below 1%, which makes the technique quite suitable and reliable for structural vibration monitoring by identifying and reproducing complex vibration modes.

Generalized channel separation algorithms for accurate camera-based multi-wavelength PTT and BP estimation

Single-site multi-wavelength (MW) pulse transit time (PTT) measurement was recently proposed using contact sensors with sequential illumination. It leverages different penetration depths of light to measure the traversal of a cardiac pulse between skin layers. This enabled continuous single-site MW blood pressure (BP) monitoring, but faces challenges like subtle skin compression, which importantly influences the PPG morphology and subsequent PTT. We extended this idea to contact-free camera-based sensing and identified the major challenge of color channel overlap, which causes the signals obtained from a consumer RGB camera to be a mixture of responses in different wavelengths, thus not allowing for meaningful PTT measurement. To address this, we propose novel camera-independent data-driven channel separation algorithms based on constrained genetic algorithms. We systematically validated the algorithms on camera recordings of palms and corresponding ground-truth BP measurements of 13 subjects in two different scenarios, rest and activity. We compared the proposed algorithms against established blind source separation methods and against previous camera-specific physics-based method, showing good performance in both PTT reconstruction and BP estimation using a Random Forest regressor. The best-performing algorithm achieved mean absolute errors (MAEs) of 3.48 and 2.61 mmHg for systolic and diastolic BP in a leave-one-subject-out experiment with personalization, solidifying the proposed algorithms as enablers of novel contact-free MW PTT and BP estimation.